Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITT
    -0.15
    alez
    -0.15
    zk
    -0.15
    efon
    -0.15
    ķĮ
    -0.14
    âĻª
    -0.14
    ardless
    -0.14
    uzzi
    -0.14
    eln
    -0.14
    shaw
    -0.14
    POSITIVE LOGITS
     about
    0.48
    about
    0.39
    åħ³äºİ
    0.35
     ABOUT
    0.33
     About
    0.33
    About
    0.32
    _about
    0.31
     tentang
    0.30
    .about
    0.28
     دربارÙĩ
    0.26
    Act Density 0.053%

    No Known Activations